Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    she

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     days
    -0.07
    Susp
    -0.06
     negligent
    -0.06
     mois
    -0.06
    (cli
    -0.06
    Put
    -0.06
    Makes
    -0.06
     Nets
    -0.06
    standing
    -0.06
     afternoon
    -0.06
    POSITIVE LOGITS
     washer
    0.07
    aphrag
    0.07
     boolean
    0.07
     lạc
    0.06
     збільш
    0.06
    uchen
    0.06
    eax
    0.06
    ,const
    0.06
     sice
    0.06
    avo
    0.06
    Act Density 0.025%

    No Known Activations